arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.06360cs.CLcs.AI
收藏

罗马尼亚语名词复合词的人工与自动解释

Human and Automatic Interpretation of Romanian Noun Compounds

Princeton University(普林斯顿大学)

Ioana Marinescu, Christiane Fellbaum

AI总结:

针对罗马尼亚语名词复合词,本文构建一套新的语义关系集,并用人工标注与神经网络分类器验证,发现模型预测与人工判断相符,但高频“无关系”暴露出现有关系清单不足。

摘要:

确定诸如“shoe sale”和“fire sale”等名词复合词依赖语境的预期含义,对NLP而言仍是一项挑战。以往工作依赖语义关系清单,用以捕捉复合词成员之间的不同含义。本文聚焦罗马尼亚语复合词,其形态句法不同于英语对应形式;我们提出一组新的关系,并通过人工标注者和一个神经网络分类器对其进行测试。结果显示,即使在人工一致率较低的情况下,该网络的预测仍与人工判断保持一致。无论结构差异如何,一致性都与所选关系的频率相关。然而,最常被选择的关系并不属于16种已标注语义关系中的任何一种,这表明需要更好的关系清单。

英文摘要:

Determining the intended, context-dependent meanings of noun compounds like "shoe sale" and "fire sale" remains a challenge for NLP. Previous work has relied on inventories of semantic relations that capture the different meanings between compound members. Focusing on Romanian compounds, whose morphosyntax differs from that of their English counterparts, we propose a new set of relations and test it with human annotators and a neural net classifier. Results show an alignment of the network's predictions and human judgments, even where the human agreement rate is low. Agreement tracks with the frequency of the selected relations, regardless of structural differences. However, the most frequently selected relation was none of the sixteen labeled semantic relations, indicating the need for a better relation inventory.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑